Innovative approach for porting existing CPU program to its CUDA program

Yu Liu; Yang Hong; Chung Hung Wang; Sheng Ta Lee; Chun Yuan Lin; Che Lun Hung

doi:10.1109/BIBM.2015.7359898

Innovative approach for porting existing CPU program to its CUDA program

Yu Liu, Yang Hong, Chung Hung Wang, Sheng Ta Lee, Chun Yuan Lin, Che Lun Hung^*

^*此作品的通信作者

研究成果: 圖書/報告稿件的類型 › 會議稿件 › 同行評審

摘要

GPU computing has gradually become the mainstream to do high-speed computing fields, such as the meteorology, image and video processing, fluid dynamics simulation, seismic analysis, and etc. How to efficiently port an existing program on CPU to its CUDA program on GPU is an important issue. From the previous works, the porting approach can be generalized and classified into two categories: Rewrite Parallel Algorithm (abbreviate to RPA) and Modify Original Library (abbreviate to MOL). For the RPA, the programmers need to understand the original sequential or parallel algorithm on CPU absolutely and then write the CUDA program on GPU directly. For the MOL, the programmers need to analyze (profile) the existing program on CPU at first to find the most spend time libraries (or functions), then they are modified greatly (rewritten in general) to become CUDA programs (kernel functions). There are several disadvantages for the RPA and MOL, especially for the porting time and executing results. Hence, in this paper, a new approach, called innovative systematic contract (abbreviate to ISC), is proposed to allow programmers to port an existing CPU program to its CUDA program by modifying the libraries lightly. The program, BLASTN v2.2.27, was ported into a CUDA version, called CUDA-BLASTN v1, by the ISC. From the experimental results, by comparing with BLASTN v2.2.27, CUDA-BLASTN v1 achieves 5x speedup ratio and obtains almost the same executing results.

原文	英語
主出版物標題	Proceedings - 2015 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015
編輯	lng. Matthieu Schapranow, Jiayu Zhou, Xiaohua Tony Hu, Bin Ma, Sanguthevar Rajasekaran, Satoru Miyano, Illhoi Yoo, Brian Pierce, Amarda Shehu, Vijay K. Gombar, Brian Chen, Vinay Pai, Jun Huan
發行者	Institute of Electrical and Electronics Engineers Inc.
頁面	1503-1508
頁數	6
ISBN（電子）	9781467367981
DOIs	https://doi.org/10.1109/BIBM.2015.7359898
出版狀態	已出版 - 16 12 2015
事件	IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015 - Washington, 美國持續時間: 09 11 2015 → 12 11 2015

出版系列

名字	Proceedings - 2015 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015

Conference

Conference	IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015
國家/地區	美國
城市	Washington
期間	09/11/15 → 12/11/15

文獻附註

Publisher Copyright:
© 2015 IEEE.

存取文件

10.1109/BIBM.2015.7359898

其它文件與鏈接

Link to publication in Scopus

引用此

Liu, Y., Hong, Y., Wang, C. H., Lee, S. T., Lin, C. Y., & Hung, C. L. (2015). Innovative approach for porting existing CPU program to its CUDA program. 於 L. M. Schapranow, J. Zhou, X. T. Hu, B. Ma, S. Rajasekaran, S. Miyano, I. Yoo, B. Pierce, A. Shehu, V. K. Gombar, B. Chen, V. Pai, & J. Huan (編輯), Proceedings - 2015 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015 (頁 1503-1508). 文章 7359898 (Proceedings - 2015 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BIBM.2015.7359898

Liu, Yu ; Hong, Yang ; Wang, Chung Hung 等. / Innovative approach for porting existing CPU program to its CUDA program. Proceedings - 2015 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015. 編輯 / lng. Matthieu Schapranow ; Jiayu Zhou ; Xiaohua Tony Hu ; Bin Ma ; Sanguthevar Rajasekaran ; Satoru Miyano ; Illhoi Yoo ; Brian Pierce ; Amarda Shehu ; Vijay K. Gombar ; Brian Chen ; Vinay Pai ; Jun Huan. Institute of Electrical and Electronics Engineers Inc., 2015. 頁 1503-1508 (Proceedings - 2015 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015).

@inproceedings{d9d54131065843fc82d31dcb046efc19,

title = "Innovative approach for porting existing CPU program to its CUDA program",

abstract = "GPU computing has gradually become the mainstream to do high-speed computing fields, such as the meteorology, image and video processing, fluid dynamics simulation, seismic analysis, and etc. How to efficiently port an existing program on CPU to its CUDA program on GPU is an important issue. From the previous works, the porting approach can be generalized and classified into two categories: Rewrite Parallel Algorithm (abbreviate to RPA) and Modify Original Library (abbreviate to MOL). For the RPA, the programmers need to understand the original sequential or parallel algorithm on CPU absolutely and then write the CUDA program on GPU directly. For the MOL, the programmers need to analyze (profile) the existing program on CPU at first to find the most spend time libraries (or functions), then they are modified greatly (rewritten in general) to become CUDA programs (kernel functions). There are several disadvantages for the RPA and MOL, especially for the porting time and executing results. Hence, in this paper, a new approach, called innovative systematic contract (abbreviate to ISC), is proposed to allow programmers to port an existing CPU program to its CUDA program by modifying the libraries lightly. The program, BLASTN v2.2.27, was ported into a CUDA version, called CUDA-BLASTN v1, by the ISC. From the experimental results, by comparing with BLASTN v2.2.27, CUDA-BLASTN v1 achieves 5x speedup ratio and obtains almost the same executing results.",

keywords = "BLAST, CUDA, GPU, Parallel Processing, Porting method",

author = "Yu Liu and Yang Hong and Wang, {Chung Hung} and Lee, {Sheng Ta} and Lin, {Chun Yuan} and Hung, {Che Lun}",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015 ; Conference date: 09-11-2015 Through 12-11-2015",

year = "2015",

month = dec,

day = "16",

doi = "10.1109/BIBM.2015.7359898",

language = "英语",

series = "Proceedings - 2015 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1503--1508",

editor = "Schapranow, {lng. Matthieu} and Jiayu Zhou and Hu, {Xiaohua Tony} and Bin Ma and Sanguthevar Rajasekaran and Satoru Miyano and Illhoi Yoo and Brian Pierce and Amarda Shehu and Gombar, {Vijay K.} and Brian Chen and Vinay Pai and Jun Huan",

booktitle = "Proceedings - 2015 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015",

address = "美国",

}

Liu, Y, Hong, Y, Wang, CH, Lee, ST, Lin, CY & Hung, CL 2015, Innovative approach for porting existing CPU program to its CUDA program. 於 LM Schapranow, J Zhou, XT Hu, B Ma, S Rajasekaran, S Miyano, I Yoo, B Pierce, A Shehu, VK Gombar, B Chen, V Pai & J Huan (編輯), Proceedings - 2015 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015., 7359898, Proceedings - 2015 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015, Institute of Electrical and Electronics Engineers Inc., 頁 1503-1508, IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015, Washington, 美國, 09/11/15. https://doi.org/10.1109/BIBM.2015.7359898

Innovative approach for porting existing CPU program to its CUDA program. / Liu, Yu; Hong, Yang; Wang, Chung Hung 等.
Proceedings - 2015 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015. 編輯 / lng. Matthieu Schapranow; Jiayu Zhou; Xiaohua Tony Hu; Bin Ma; Sanguthevar Rajasekaran; Satoru Miyano; Illhoi Yoo; Brian Pierce; Amarda Shehu; Vijay K. Gombar; Brian Chen; Vinay Pai; Jun Huan. Institute of Electrical and Electronics Engineers Inc., 2015. p. 1503-1508 7359898 (Proceedings - 2015 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015).

研究成果: 圖書/報告稿件的類型 › 會議稿件 › 同行評審

TY - GEN

T1 - Innovative approach for porting existing CPU program to its CUDA program

AU - Liu, Yu

AU - Hong, Yang

AU - Wang, Chung Hung

AU - Lee, Sheng Ta

AU - Lin, Chun Yuan

AU - Hung, Che Lun

PY - 2015/12/16

Y1 - 2015/12/16

N2 - GPU computing has gradually become the mainstream to do high-speed computing fields, such as the meteorology, image and video processing, fluid dynamics simulation, seismic analysis, and etc. How to efficiently port an existing program on CPU to its CUDA program on GPU is an important issue. From the previous works, the porting approach can be generalized and classified into two categories: Rewrite Parallel Algorithm (abbreviate to RPA) and Modify Original Library (abbreviate to MOL). For the RPA, the programmers need to understand the original sequential or parallel algorithm on CPU absolutely and then write the CUDA program on GPU directly. For the MOL, the programmers need to analyze (profile) the existing program on CPU at first to find the most spend time libraries (or functions), then they are modified greatly (rewritten in general) to become CUDA programs (kernel functions). There are several disadvantages for the RPA and MOL, especially for the porting time and executing results. Hence, in this paper, a new approach, called innovative systematic contract (abbreviate to ISC), is proposed to allow programmers to port an existing CPU program to its CUDA program by modifying the libraries lightly. The program, BLASTN v2.2.27, was ported into a CUDA version, called CUDA-BLASTN v1, by the ISC. From the experimental results, by comparing with BLASTN v2.2.27, CUDA-BLASTN v1 achieves 5x speedup ratio and obtains almost the same executing results.

AB - GPU computing has gradually become the mainstream to do high-speed computing fields, such as the meteorology, image and video processing, fluid dynamics simulation, seismic analysis, and etc. How to efficiently port an existing program on CPU to its CUDA program on GPU is an important issue. From the previous works, the porting approach can be generalized and classified into two categories: Rewrite Parallel Algorithm (abbreviate to RPA) and Modify Original Library (abbreviate to MOL). For the RPA, the programmers need to understand the original sequential or parallel algorithm on CPU absolutely and then write the CUDA program on GPU directly. For the MOL, the programmers need to analyze (profile) the existing program on CPU at first to find the most spend time libraries (or functions), then they are modified greatly (rewritten in general) to become CUDA programs (kernel functions). There are several disadvantages for the RPA and MOL, especially for the porting time and executing results. Hence, in this paper, a new approach, called innovative systematic contract (abbreviate to ISC), is proposed to allow programmers to port an existing CPU program to its CUDA program by modifying the libraries lightly. The program, BLASTN v2.2.27, was ported into a CUDA version, called CUDA-BLASTN v1, by the ISC. From the experimental results, by comparing with BLASTN v2.2.27, CUDA-BLASTN v1 achieves 5x speedup ratio and obtains almost the same executing results.

KW - BLAST

KW - CUDA

KW - GPU

KW - Parallel Processing

KW - Porting method

UR - http://www.scopus.com/inward/record.url?scp=84962448822&partnerID=8YFLogxK

U2 - 10.1109/BIBM.2015.7359898

DO - 10.1109/BIBM.2015.7359898

M3 - 会议稿件

AN - SCOPUS:84962448822

T3 - Proceedings - 2015 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015

SP - 1503

EP - 1508

BT - Proceedings - 2015 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015

A2 - Schapranow, lng. Matthieu

A2 - Zhou, Jiayu

A2 - Hu, Xiaohua Tony

A2 - Ma, Bin

A2 - Rajasekaran, Sanguthevar

A2 - Miyano, Satoru

A2 - Yoo, Illhoi

A2 - Pierce, Brian

A2 - Shehu, Amarda

A2 - Gombar, Vijay K.

A2 - Chen, Brian

A2 - Pai, Vinay

A2 - Huan, Jun

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015

Y2 - 9 November 2015 through 12 November 2015

ER -

Liu Y, Hong Y, Wang CH, Lee ST, Lin CY, Hung CL. Innovative approach for porting existing CPU program to its CUDA program. 於 Schapranow LM, Zhou J, Hu XT, Ma B, Rajasekaran S, Miyano S, Yoo I, Pierce B, Shehu A, Gombar VK, Chen B, Pai V, Huan J, 編輯, Proceedings - 2015 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015. Institute of Electrical and Electronics Engineers Inc. 2015. p. 1503-1508. 7359898. (Proceedings - 2015 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015). doi: 10.1109/BIBM.2015.7359898

Innovative approach for porting existing CPU program to its CUDA program

摘要

出版系列

Conference

文獻附註

存取文件

其它文件與鏈接

指紋

引用此